Task not serializable

出问题代码：

package com.data.Spark_learn;

import java.util.Arrays;
import java.util.Iterator;

import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.junit.Test;

/**
 * 
 * @author 小二狗
 *
 */
public class Learn {
	@Test
	public void test3() {
		SparkConf conf = new SparkConf().setMaster("local").setAppName("wzz1");
		JavaSparkContext sc = new JavaSparkContext(conf);
		JavaRDD<String> parallelize = sc.parallelize(Arrays.asList("this is a book", "an apple", "book is apple"));
		JavaRDD<String> flatMap = parallelize.flatMap(new FlatMapFunction<String, String>() {

			@Override
			public Iterator<String> call(String t) throws Exception {
				return Arrays.asList(t.split(" ")).iterator();
			}
		});
		System.out.println(StringUtils.join(flatMap.collect(), ","));
		sc.close();
	}
}

报错：

org.apache.spark.SparkException: Task not serializable
	at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:345)
	at org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:335)
	at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:159)
	at org.apache.spark.SparkContext.clean(SparkContext.scala:2299)
	at org.apache.spark.rdd.RDD$$anonfun$flatMap$1.apply(RDD.scala:380)
	at org.apache.spark.rdd.RDD$$anonfun$flatMap$1.apply(RDD.scala:379)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
	at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
	at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
	at org.apache.spark.rdd.RDD.flatMap(RDD.scala:379)
	at org.apache.spark.api.java.JavaRDDLike$class.flatMap(JavaRDDLike.scala:126)
	at org.apache.spark.api.java.AbstractJavaRDDLike.flatMap(JavaRDDLike.scala:45)
	at com.data.Spark_learn.Learn.test3(Learn.java:24)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
	at java.lang.reflect.Method.invoke(Method.java:498)
	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
	at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:86)
	at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38)
	at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:538)
	at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:760)
	at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:460)
	at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:206)
Caused by: java.io.NotSerializableException: com.data.Spark_learn.Learn
Serialization stack:
	- object not serializable (class: com.data.Spark_learn.Learn, value: com.data.Spark_learn.Learn@2bf94401)
	- field (class: com.data.Spark_learn.Learn$1, name: this$0, type: class com.data.Spark_learn.Learn)
	- object (class com.data.Spark_learn.Learn$1, com.data.Spark_learn.Learn$1@2098d37d)
	- field (class: org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$1$1, name: f$3, type: interface org.apache.spark.api.java.function.FlatMapFunction)
	- object (class org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$1$1, <function1>)
	at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40)
	at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:46)
	at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
	at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:342)
	... 35 more

原因：使用map等匿名内部类的class，（例如我的Leanr类）需要序列化。也可以将匿名内部类改为具名类。

/**
 * 
 * @author 小二狗
 *
 */
public class Learn implements Serializable{
	
	/**
	 * 
	 */
	private static final long serialVersionUID = 1L;

        ...
}